A multi-parameter-based intelligent water leakage detection method and system for a water supply pipeline

Abstract

The application belongs to the technical field of water supply pipeline detection, and discloses a water supply pipeline leakage intelligent detection method and system based on multiple parameters, which comprises the following steps: S1, analyzing the entire pipe network type in the area covered by the water supply equipment, finding out the main pipeline and each branch pipeline, and installing pressure monitoring equipment on the main pipeline and each branch pipeline to collect pipe network pressure monitoring data; S2, pre-processing the obtained data by using a data preprocessing method, completing the deletion and supplement of zero points and abnormal points in the data, and enhancing the data by using a data enhancement technology to improve the data precision; S3, analyzing the pressure parameters in the entire pipeline according to a pressure drop correlation model to obtain the entire pipe network pressure model and draw a pipe network pressure drop diagram; and S4, finding out the position of the pipeline leakage according to the pressure parameter analysis result.

Description

Technical Field

[0001] This invention belongs to the field of water supply pipeline detection technology, and in particular relates to an intelligent detection method and system for water supply pipeline leakage based on multiple parameters. Background Technology

[0002] Urban water supply pipelines are not only an important infrastructure for urban construction, but also a public utility. The normal operation of the water supply network plays a crucial role in ensuring the stable development of the urban economy and the significant improvement of people's living standards. Especially at present, when water resources are scarce and environmental pollution restricts the scale of water supply, if leaks in the pipeline network are not detected and repaired in time, a large amount of water resources will be wasted, causing significant economic losses to the country.

[0003] Currently, there are many conventional methods, such as automatic leak detection by sound and sound-based leak detection. These passive leak detection methods are greatly affected by external interference, so the results produced are also more erroneous.

[0004] With the continuous development of technology and the in-depth development of big data analysis and intelligent algorithms, intelligent detection of leaks in complex water supply pipelines can be achieved by using intelligent algorithms and other means.

[0005] Based on the above analysis, the problems and shortcomings of the existing technology are as follows:

[0006] 1. Passive detection: Existing leak detection methods, such as automatic leak detection by sound and acoustic leak detection, are all passive. This means they can only detect leaks that have already occurred, but cannot actively predict or prevent leaks. This leads to longer repair times and significant water waste.

[0007] 2. Susceptible to interference: Since these methods are based on sound or hearing, they are easily affected by environmental noise or other interference, which can lead to false alarms or missed alarms.

[0008] 3. Accuracy and Reliability Issues: The accuracy and reliability of these methods largely depend on the skill and experience of the operators. Furthermore, operator fatigue and negligence can easily lead to leaks not being detected and repaired in a timely manner.

[0009] The main technical problems that need to be solved are:

[0010] 1. Improve proactive detection: We need a technology that can proactively predict and prevent leaks, so that repairs can be carried out before leaks occur, greatly reducing water waste.

[0011] 2. Anti-interference capability: In order to reduce the impact of environmental noise and other interference on detection, we need to develop a technology or algorithm that can filter out these interferences.

[0012] 3. Improve detection accuracy and reliability: We need to develop a technology or algorithm that can detect leaks more accurately and reliably, which can reduce false alarms and missed alarms and improve water resource utilization efficiency.

[0013] Existing leak detection technologies still have many areas that need improvement and optimization, while new technologies such as big data analytics and intelligent algorithms can provide us with new solutions. Summary of the Invention

[0014] To address the problems existing in the prior art, this invention provides a method and system for intelligent detection of water supply pipeline leaks based on multiple parameters. Based on the monitoring parameters collected in the pipelines within the water supply coverage area, the system uses a multiple linear regression model to perform logistic regression analysis on the acquired data, thereby understanding the hydraulic and water pressure relationship model of the entire pipeline network and building a hydraulic model of the entire complex pipeline network. This enables intelligent and accurate detection of leaks in water supply pipelines.

[0015] This invention is implemented as follows: a smart method for detecting leaks in water supply pipelines based on multiple parameters, comprising:

[0016] S1. Within the area covered by the water supply equipment, analyze the entire pipe network type, identify the main pipe and each branch pipe, and install pressure monitoring equipment on the main pipe and each branch pipe to collect pipe network pressure monitoring data.

[0017] S2, the data obtained above is preprocessed using data preprocessing methods to remove and supplement zero points and outliers in the data, and data augmentation techniques are used to enhance the data and improve data accuracy.

[0018] S3. Analyze the pressure parameters in the entire pipeline based on the pressure drop correlation model to obtain the pressure model of the entire pipeline network and draw the pipeline network pressure drop diagram.

[0019] S4. Locate the location of the pipeline leak based on the pressure parameter analysis results.

[0020] Furthermore, based on the water pressure variation model, the hydraulic system for pressure drop in the pipeline network satisfies the following correlation model:

[0021]

[0022] In the formula, This is a pressure parameter matrix. The error coefficient; It is a multi-parameter linear regression model; Input the total pressure into the pipeline; analyze the pressure parameters in the entire pipeline based on the pressure drop correlation model to obtain the pressure model of the entire pipeline network and draw the pipeline network pressure drop diagram.

[0023] Furthermore, each node in the pipeline network should satisfy the mass balance equation, namely:

[0024]

[0025] In the formula, The flow rate of the pipe segment connecting node i and node j; User traffic for node i; Let i be the leakage amount at node i;

[0026] Each pipe segment in the pipeline network satisfies the pressure drop equation:

[0027]

[0028] In the formula, P is the nodal pressure; K is the drag coefficient; This represents the flow rate between pipe segments i and j. E represents the specific gravity of the fluid; E represents the ground elevation of the node.

[0029] The leakage rate is usually an unknown quantity, expressed as a formula relating the leakage area and pressure:

[0030]

[0031] In the formula, For leakage flow; This is the leakage outlet coefficient; Let g be the equivalent leakage outlet area, and g be the gravitational acceleration.

[0032] Furthermore, the model integrates the nodal equations and pipe segment equations. To simplify calculations, it is assumed that the ground elevation of the nodal points is 0. Therefore, the model is as follows:

[0033]

[0034]

[0035] In the formula, It is a constant flow rate that does not depend on pressure changes; For a flow rate constant that depends on pressure changes; for example, the flow rate through a fixed orifice; m represents the [i,j] group, where m=1 means i=1||j=1. Indicates the measurement of water head. This represents the position of the nth node in the i-th branch network. This indicates the resistance coefficient between pipe sections. This represents a flow constant that does not depend on changes in pressure. This represents a flow constant that depends on changes in pressure. To leak the export coefficient, For the equivalent leakage outlet area, It represents the acceleration due to gravity.

[0036] Furthermore, if the standard deviation of the errors in head measurement and friction coefficient deviates from the known value, the error change in the leakage area size will be:

[0037] .

[0038] Another objective of this invention is to provide an intelligent water supply pipeline leakage detection system based on multiple parameters, comprising:

[0039] The pressure monitoring module is used to analyze the entire pipe network type within the area covered by the water supply equipment, identify the main pipe and each branch pipe, and install pressure monitoring equipment on the main pipe and each branch pipe to collect pipe network pressure monitoring data.

[0040] The data preprocessing module is used to preprocess the data obtained above using data preprocessing methods, complete the deletion and supplementation of zero points and outliers in the data, and use data augmentation technology to enhance the data and improve data accuracy.

[0041] The pressure parameter analysis module is used to analyze the pressure parameters in the entire pipeline based on the pressure drop correlation model, obtain the pressure model of the entire pipeline network, and draw the pipeline network pressure drop diagram.

[0042] The leak location analysis module is used to locate the source of pipeline leaks based on pressure parameter analysis results.

[0043] Another object of the present invention is to provide a computer device, the computer device including a memory and a processor, the memory storing a computer program, and when the computer program is executed by the processor, causing the processor to perform the steps of the intelligent detection method for water supply pipeline leakage based on multiple parameters.

[0044] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the intelligent water supply pipeline leakage detection method based on multiple parameters.

[0045] Another objective of this invention is to provide an information data processing terminal for implementing the aforementioned intelligent water supply pipeline leakage detection system based on multiple parameters.

[0046] Based on the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solution to be protected by this invention are as follows:

[0047] First, this invention utilizes monitoring parameters collected from pipelines within the water supply coverage area. By employing a multiple linear regression model, it performs logistic regression analysis on the acquired data to determine the hydraulic and water pressure relationship model of the entire pipeline network. This allows for the construction of a comprehensive hydraulic model of the complex pipeline network, enabling intelligent and precise detection of leaks in water supply pipelines. This invention offers advantages such as intelligence, real-time monitoring, human-computer interaction, strong resistance to environmental interference, and high versatility.

[0048] Secondly, the intelligent water supply pipeline leakage detection method based on multiple parameters of this invention brings the following significant technological advancements:

[0049] 1) Real-time and accurate leak detection: By monitoring pipeline pressure parameters in real time and applying a pressure drop correlation model, this method can detect the location of pipeline leaks in real time and accurately, greatly improving the efficiency and accuracy of leak detection.

[0050] 2) Data Preprocessing and Augmentation: By preprocessing and augmenting the raw data, the quality of the data and the accuracy of the model can be improved. Data preprocessing can eliminate outliers and noise in the data, while data augmentation can increase the generalization ability of the model, enabling the model to better handle various real-world situations.

[0051] 3) Comprehensive utilization of multiple parameters: This method does not only consider a single pressure parameter, but comprehensively considers multiple parameters, including the pressure parameters of the main pipeline and each branch pipeline, as well as the relationship between these parameters, which can provide a more comprehensive and in-depth understanding of the working status of the pipeline system.

[0052] 4) Wide range of applications: This method is applicable to various types of water supply pipeline systems, including urban water supply systems and factory water supply systems, and has broad application prospects.

[0053] 5) Reduced maintenance costs: Real-time and accurate leak detection can prevent the waste of large amounts of water resources caused by leaks and allow for timely repair of leak points, thereby reducing maintenance costs and environmental impact.

[0054] The intelligent leak detection method for water supply pipelines based on multiple parameters provided by this invention enables real-time, accurate, and comprehensive leak detection, improves detection efficiency and accuracy, reduces maintenance costs and environmental impact, and has significant technological advancements.

[0055] Third, the expected benefits and commercial value of the technical solution of this invention after transformation are as follows: This invention is of great significance for the in-depth application of current smart water supply and smart peak regulation systems. After the results are transformed, it can solve the current technical problems in water supply, change the previous method of relying on manual labor, instruments and other conventional means to detect leaks, and reduce a lot of manpower. Attached Figure Description

[0056] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a flowchart of the intelligent water supply pipeline leakage detection method based on multiple parameters provided in the embodiments of the present invention;

[0058] Figure 2 This is a schematic diagram of the intelligent water supply pipeline leakage detection system based on multiple parameters provided in an embodiment of the present invention;

[0059] Figure 3 This is a schematic diagram of the water supply network provided in an embodiment of the present invention;

[0060] Figure 4 This is a schematic diagram of pressure data collected in a water supply area according to an embodiment of the present invention;

[0061] Figure 5 This is a schematic diagram of pressure data from a burst water supply pipe in a certain water supply area, provided in an embodiment of the present invention. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0063] To address the problems existing in the prior art, the present invention provides an intelligent method and system for detecting water leakage in water supply pipelines based on multiple parameters. The present invention will be described in detail below with reference to the accompanying drawings.

[0064] Explanatory and illustrative embodiments. To enable those skilled in the art to fully understand how the present invention is specifically implemented, this section provides an explanatory and illustrative description of the embodiments described in the claims.

[0065] like Figure 1 As shown, the intelligent leak detection method for water supply pipelines based on multiple parameters includes:

[0066] S1. Within the area covered by the water supply equipment, analyze the entire pipe network type, identify the main pipe and each branch pipe, and install pressure monitoring equipment on the main pipe and each branch pipe to collect pipe network pressure monitoring data.

[0067] S2, the data obtained above is preprocessed using data preprocessing methods to remove and supplement zero points and outliers in the data, and data augmentation techniques are used to enhance the data and improve data accuracy.

[0068] S3. Analyze the pressure parameters in the entire pipeline based on the pressure drop correlation model to obtain the pressure model of the entire pipeline network and draw the pipeline network pressure drop diagram.

[0069] S4. Locate the location of the pipeline leak based on the pressure parameter analysis results.

[0070] like Figure 2 As shown, the intelligent water supply pipeline leakage detection system based on multiple parameters includes:

[0071] The pressure monitoring module is used to analyze the entire pipe network within the area covered by the water supply equipment, identify the main pipe and each branch pipe, and install pressure monitoring equipment on the main pipe and each branch pipe to collect pipe network pressure monitoring data.

[0072] The data preprocessing module is used to preprocess the data obtained above using data preprocessing methods, complete the deletion and supplementation of zero points and outliers in the data, and use data augmentation technology to enhance the data and improve data accuracy.

[0073] The pressure parameter analysis module is used to analyze the pressure parameters in the entire pipeline based on the pressure drop correlation model, obtain the pressure model of the entire pipeline network, and draw the pipeline network pressure drop diagram.

[0074] The leak location analysis module is used to locate the source of pipeline leaks based on pressure parameter analysis results.

[0075] The main implementation scheme of the intelligent leakage detection method for complex water supply pipelines provided in this invention is as follows:

[0076] Within the area covered by the water supply equipment, the entire pipe network type is analyzed to identify the main pipe and all branch pipes. Pressure monitoring equipment is then installed on the main pipe and all branch pipes. A schematic diagram of the installation of each monitoring device is shown below. Figure 4 The hydraulic monitoring parameters of the entire pipeline network were completed, and the collected parameters are as follows:

[0077] (1) Total pressure of the main pipeline (P1);

[0078] (2) Pipe pressure of branch pipe 1 (P_z1);

[0079] (3) Pipe pressure of branch pipe 2 (P_z2);

[0080] (4) Pipe pressure of branch pipe 3 (P_z3);

[0081] (5) Pipe pressure of branch pipe 4 (P_z4);

[0082] (6) Pipe pressure of branch pipe 5 (P_z5);

[0083] (7) Pipe pressure of branch pipe 6 (P_z6);

[0084] (8) Pipe pressure of branch pipe 7 (P_z7);

[0085] (9) Pipe pressure (P_z8) of branch pipe 8;

[0086] …

[0087] (30) Pipe pressure of branch pipe 39 (P_z29).

[0088] The data obtained above is preprocessed using data preprocessing methods to remove and supplement zero points and outliers in the data;

[0089] Since the original data size is between 0 and 1, data augmentation techniques are used to enhance the data and improve its accuracy.

[0090] Based on the obtained data and the pipeline network hydraulic dynamic model, the water pressure change in the pipeline network is linear. The pressure value is highest at the outlet of the water supply equipment, and the water pressure changes in a stepwise manner to the most unfavorable monitoring point. Furthermore, the water pressure between pipes changes linearly. Therefore, according to the water pressure change relationship model, the pipeline network pressure drop hydraulic system satisfies the following correlation model:

[0091]

[0092] In the formula:

[0093] —Pressure parameter matrix;

[0094] —Error coefficient;

[0095] —Multi-parameter linear regression model;

[0096] —Total pressure input to the pipeline.

[0097] Based on the above analysis, the pressure parameters in the entire pipeline can be analyzed according to the pressure drop correlation model, and the pressure model of the entire pipeline network can be obtained, thereby enabling the plotting of the pipeline network pressure drop diagram.

[0098] If a pipe bursts or leaks in a certain area, the pressure drop in that area will be significant. If the pressure does not recover within a certain period of time, it indicates that the section of the pipeline has burst or leaked.

[0099] Based on the given hydraulic model of pipeline pressure drop, the key problem of this invention is how to solve this model. In typical hydraulic system analysis, water consumption and system characteristics are known, and the aim is to find the distribution of pressure and flow. The system characteristics and flow rate are known, but some quantities (unexplained node outflows, i.e., leaks) are unknown. If the known quantities can include a sufficient number of pressure values, such as pressure monitoring values, then the leakage can be found at least theoretically.

[0100] From the perspective of pipeline hydraulics theory, each node in the pipeline network should satisfy the mass balance equation, that is:

[0101] (1)

[0102] In the formula:

[0103] —The flow rate of the pipe segment connecting node i and node j. ;

[0104] —User traffic at node i ;

[0105] —Leakage amount of node i ;

[0106] In addition, each pipe segment in the pipeline network satisfies the pressure drop equation:

[0107] (2)

[0108] In the formula:

[0109] P – Nodal pressure, MPa;

[0110] K – Resistance coefficient, including factors such as pipe diameter;

[0111] —The flow rate between pipe segments i and j;

[0112] —Fluid specific gravity;

[0113] E – Node ground elevation, in meters (m).

[0114] The leakage rate is usually unknown, but it can be expressed as a formula relating the leakage area and pressure:

[0115] (3)

[0116] In the formula:

[0117] —Leakage flow;

[0118] —Leakage exit coefficient;

[0119] —Equivalent leakage outlet area, ;

[0120] — Same as above.

[0121] In this way, it can be used As an unknown quantity This has certain advantages because Not independent, but They are independent variables.

[0122] The model integrates the nodal equations and pipe segment equations. To simplify calculations, it is assumed that the ground elevation of the nodal points is 0. The model is as follows:

[0123] (4)

[0124] (5)

[0125] In the formula:

[0126] —A flow constant that does not depend on pressure changes. ;

[0127] —A flow constant dependent on pressure changes; for example, the flow rate exiting through a fixed orifice. ;

[0128] As can be seen from the above formula, if the export coefficient is given a fixed value... Then the unknowns are some quantities that have not been measured. and all This equation is a series of overstable, nonlinear equations that can be solved using the Levenberg-Marquardt method.

[0129] This solution is based on minimizing the difference between the measured and calculated values, and the objective function is defined as:

[0130] (6)

[0131] In the formula:

[0132] —Number of measurement points;

[0133] —Measured water head at monitoring point i, ;

[0134] — Measurement error (standard deviation) at point i, m;

[0135] --by Let m be the calculated head value at the i-th monitoring point of the independent variable.

[0136] Take the objective function pair The differential yields:

[0137] (7)

[0138] The second derivative is:

[0139] (8)

[0140] Define the Hessian matrix

[0141] Generally, the second term in equation (8) can be ignored, then we get:

[0142] (9)

[0143] This can be expressed as:

[0144]

[0145] The above model solution process assumes that the measurements are error-free. However, in reality, there are errors in the measurement of water head and the determination of pipe friction. Therefore, the reliability of the solution can be obtained from the sensitivity list.

[0146] The formula for calculating Hayzen-Williams is as follows:

[0147]

[0148] In the formula:

[0149] --flow, ;

[0150] — Pipe length, in meters;

[0151] —Inner diameter, m;

[0152] — Coefficients: C=150 for plastic pipes, C=130 for new cast iron pipes, C=120 for concrete pipes, and C=100 for old cast iron pipes and old steel pipes.

[0153] Typically, an equation concerning nodal head can be implicitly expressed as:

[0154] (11)

[0155] In the formula:

[0156] —The best estimate of the leakage area;

[0157] —The best estimate of the Hayzen-Williams coefficient.

[0158] Right now: (12)

[0159] Expanding equation (12) in Taylor series, we get:

[0160] (13)

[0161] From the above formula, (14)

[0162] If the standard deviation of the errors in head measurement and friction coefficient deviates from the known value, then the error in the leakage area size will change as follows:

[0163] (15)

[0164] Based on the above inverse analysis method leak location model and model error analysis, it can be seen that in order to obtain reliable results in the quasi-problem calculation, the pipe friction coefficient must be known; otherwise, the solution may not meet the requirements.

[0165] An application embodiment of the present invention provides a computer device, which includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the processor performs the steps of a smart detection method for water supply pipeline leakage based on multiple parameters.

[0166] An application embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of a smart water supply pipeline leakage detection method based on multiple parameters.

[0167] This invention provides an information data processing terminal for implementing a multi-parameter-based intelligent leak detection system for water supply pipelines. # Embodiment of an Intelligent Leak Detection Method for Water Supply Pipelines Based on Multi-parameters

[0168] The following are two specific examples illustrating how to use a smart leak detection method for water supply pipelines based on multiple parameters.

[0169] Example 1:

[0170] Field equipment and data collection:

[0171] Within the water supply coverage area of ​​a city, the first step is to analyze the entire pipe network to identify the main pipe and all branch pipes. Then, pressure monitoring equipment is installed; this equipment can be wireless pressure sensors with IoT capabilities, capable of sending pipe pressure data to a central server in real time.

[0172] Data preprocessing and augmentation:

[0173] The collected data is first preprocessed. For example, zero points and outliers are identified and removed through automatic detection and manual verification. Then, data augmentation techniques such as random noise insertion and data augmentation are used to enhance the data, thereby improving the accuracy of the data and the generalization ability of the model.

[0174] Voltage drop model analysis and leak detection:

[0175] A pressure drop correlation model was established to analyze the pressure parameters throughout the pipeline, resulting in a pressure model for the entire pipeline network, and a pressure drop diagram of the network was plotted. Then, by comparing real-time pressure data with model prediction data, the location of pipeline leaks was identified.

[0176] Example 2:

[0177] Field equipment and data collection:

[0178] Within the water supply area of ​​a factory, the first step is to analyze the entire pipe network to identify the main pipe and all branch pipes. Then, pressure monitoring equipment, which can be wired pressure sensors, is installed to collect pipe pressure data in real time through a field control system.

[0179] Data preprocessing and augmentation:

[0180] The collected data is first preprocessed. For example, zero points and outliers are identified and removed through automatic detection and manual verification. Then, data augmentation techniques such as data scaling and data shifting are used to enhance the data, thereby improving its accuracy and the model's generalization ability.

[0181] Voltage drop model analysis and leak detection:

[0182] A pressure drop correlation model was established to analyze the pressure parameters throughout the pipeline, resulting in a pressure model for the entire pipeline network, and a pressure drop diagram of the network was plotted. Then, by comparing real-time pressure data with model prediction data, the location of pipeline leaks was identified.

[0183] In both embodiments, the basic steps of the intelligent leak detection method for water supply pipelines based on multiple parameters are the same. However, different pressure monitoring equipment and data augmentation technologies can be selected for different site conditions and needs to achieve the best leak detection effect.

[0184] It should be noted that embodiments of the present invention can be implemented in hardware, software, or a combination of both. The hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by a suitable instruction execution system, such as a microprocessor or dedicated-design hardware. Those skilled in the art will understand that the above-described devices and methods can be implemented using computer-executable instructions and / or included in processor control code, for example, such code provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The devices and modules of the present invention can be implemented by hardware circuitry such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field-programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of the above-described hardware circuitry and software, such as firmware.

[0185] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions, and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention, and within the spirit and principles of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A smart method for detecting leaks in water supply pipelines based on multiple parameters, characterized in that, include: S1. Within the area covered by the water supply equipment, analyze the entire pipe network type, identify the main pipe and each branch pipe, and install pressure monitoring equipment on the main pipe and each branch pipe to collect pipe network pressure monitoring data. S2, the data obtained above is preprocessed using data preprocessing methods to remove and supplement zero points and outliers in the data, and data augmentation techniques are used to enhance the data and improve data accuracy. S3. Analyze the pressure parameters in the entire pipeline based on the pressure drop correlation model to obtain the pressure model of the entire pipeline network and draw the pipeline network pressure drop diagram. S4. Locate the location of the pipeline leak based on the pressure parameter analysis results; Based on the water pressure variation model, the hydraulic system for pressure drop in the pipeline network satisfies the following correlation model: ； In the formula, This is a pressure parameter matrix. The error coefficient; It is a multi-parameter linear regression model; Input the total pressure into the pipeline; analyze the pressure parameters in the entire pipeline based on the pressure drop correlation model to obtain the pressure model of the entire pipeline network and draw the pipeline network pressure drop diagram; Each node in the pipeline network should satisfy the mass balance equation, that is: ； In the formula, The flow rate of the pipe segment connecting node i and node j; User traffic for node i; Let i be the leakage amount at node i; Each pipe segment in the pipeline network satisfies the pressure drop equation: ； In the formula, P is the nodal pressure; K is the drag coefficient; This represents the flow rate between pipe segments i and j. E represents the fluid specific gravity; E represents the node ground elevation. The leakage rate is usually an unknown quantity, expressed as a formula relating the leakage area and pressure: ； In the formula, For leakage flow; This is the leakage outlet coefficient; Let g be the equivalent leakage outlet area, and g be the gravitational acceleration. The model integrates the nodal equations and pipe segment equations. To simplify calculations, it is assumed that the ground elevation of the nodal points is 0. The model is as follows: ； ； In the formula, It is a constant flow rate that does not depend on pressure changes; A flow constant that depends on pressure changes; m represents the union of [i,j], and m=1 means i=1||j=1. Indicates the measurement of water head. This represents the position of the nth node in the i-th branch network. This indicates the resistance coefficient between pipe sections. This represents a flow constant that does not depend on changes in pressure. This represents a flow constant that depends on changes in pressure. To leak the export coefficient, For the equivalent leakage export area, Represents gravitational acceleration; If the standard deviation of the errors in head measurement and friction coefficient deviates from the known value, then the error in the leakage area size will change as follows: 。 2. A multi-parameter-based intelligent water supply pipeline leakage detection system that implements the multi-parameter-based intelligent water supply pipeline leakage detection method as described in claim 1, characterized in that, include: The pressure monitoring module is used to analyze the entire pipe network within the area covered by the water supply equipment, identify the main pipe and each branch pipe, and install pressure monitoring equipment on the main pipe and each branch pipe to collect pipe network pressure monitoring data. The data preprocessing module is used to preprocess the data obtained above using data preprocessing methods, complete the deletion and supplementation of zero points and outliers in the data, and use data augmentation technology to enhance the data and improve data accuracy. The pressure parameter analysis module is used to analyze the pressure parameters in the entire pipeline based on the pressure drop correlation model, obtain the pressure model of the entire pipeline network, and draw the pipeline network pressure drop diagram. The leak location analysis module is used to locate the source of pipeline leaks based on pressure parameter analysis results.

3. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the intelligent water supply pipeline leakage detection method based on multiple parameters as described in claim 1.

4. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor performs the steps of the intelligent water supply pipeline leakage detection method based on multiple parameters as described in claim 1.

5. An information data processing terminal, which is used to implement the intelligent water supply pipeline leakage detection system based on multiple parameters as described in claim 2.

Images